Hakmin Kim
Machine Learning Engineer at Intel corporation
Seoul, South Korea
Summary
🤩
Rockstar🎓
Top SchoolHakmin Kim is a machine learning engineer and hardware specialist with over 20 years in IT, spanning hardware engineering, field application engineering, and technical marketing across automotive, mobile, and IoT domains. He led HW and PM efforts for smart infotainment and cockpit projects with Hyundai/KIA Mobis and GM/LG, and supported tablet and smartphone platforms at Motorola and Intel. More recently he has focused on ML inference performance, contributing backend and kernel optimizations to the widely used OpenVINO toolkit, improving CLDNN broadcasting and reduce primitives for real-world kernels. Based in Seoul, he combines low-level performance tuning with systems-level product experience, enabling deployment of AI on constrained devices and embedded platforms. His background in radio sciences and long tenure in both product and engineering roles give him a pragmatic edge for turning complex hardware-software constraints into production-ready solutions.
5 years of coding experience
21 years of employment as a software developer
학사, Radio Sciences Engineering, 학사, Radio Sciences Engineering at 한국해양대학교
Github Skills (15)
performance-tuning10
computer-vision10
optimizer10
performance-monitor10
c-language10
deep-learning10
performance-monitoring10
performance-analysis10
cprogramming-language10
performance-analytics10
optimisation10
performance-measurement10
optimization10
ai9
inference9
Programming languages (2)
Github contributions (5)
openvinotoolkit/openvino
Feb 2021 - Jan 2023
OpenVINO™ is an open source toolkit for optimizing and deploying AI inference
Role in this project:
Back-end Developer & Performance Engineer
Back-end Developer & Performance EngineerContributions:323 reviews, 40 commits, 159 PRs in 1 year 10 months
Contributions summary:Hakmin's commits focused on optimizing and fixing issues within the OpenVINO™ toolkit's CLDNN (Convolutional Neural Network for Deep Learning) backend. Their primary contributions involved addressing reduce accumulate issues in unit tests, supporting broadcasting in eltwise operations for specific layer formats (b_fs_yx_fsv16), and fixing regressions related to this functionality. They also worked on using single primitive reduce when the axis is along the feature dimension and various optimizations in gemm and other kernels like b_fs_zyx_fsv16.
inference-enginepytorchmodel-optimizerdeep-learninggpu
hyunback/openvino
Feb 2021 - Apr 2025
OpenVINO™ Toolkit repository
Contributions:474 pushes, 224 branches in 4 years 2 months
pytorchdeep-learninggpuopenvino-toolkitcomputer-vision
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.